Apply suggestions from code review

Co-authored-by: Piyush Jain <piyushjain@duck.com>
Co-authored-by: david qiu <david@qiu.dev>

docs/source/users/index.md

@@ -357,27 +357,9 @@ GPT4All support is still an early-stage feature, so some bugs may be encountered
 during usage. Our team is still actively improving support for locally-hosted
 models.
 
-### Ollama usage (early-stage)
+### Ollama usage
 
-Jupyter AI provides basic support for Ollama models.
-
-To get started, follow the instructions on the [Ollama website](https://ollama.com/) to set up `ollama` and download the models locally. Currently Jupyter AI only supports the following models:
-
-- `gemma`
-- `gemma2`
-- `llama2`,
-- `llama3`,
-- `llama3:70b`,
-- `phi3`,
-- `mistral`,
-- `tinyllama`,
-- `qwen2`,
-- `qwen2:7b`,
-- `qwen2:72b`,
-
-:::{note}
-There are plans to make the list of Ollama models configurable in the future, so users can download more models available via Ollama.
-:::
+To get started, follow the instructions on the [Ollama website](https://ollama.com/) to set up `ollama` and download the models locally. To select a model, enter the model name in the settings panel, for example `deepseek-coder-v2`.
 
 ### Asking about something in your notebook
 

packages/jupyter-ai-magics/jupyter_ai_magics/embedding_providers.py

@@ -70,18 +70,12 @@ def __init__(self, *args, **kwargs):
 class OllamaEmbeddingsProvider(BaseEmbeddingsProvider, OllamaEmbeddings):
     id = "ollama"
     name = "Ollama"
+    # source: https://ollama.com/library
     models = [
-        "gemma",
-        "gemma2",
-        "llama2",
-        "llama3",
-        "llama3:70b",
-        "phi3",
-        "mistral",
-        "tinyllama",
-        "qwen2",
-        "qwen2:7b",
-        "qwen2:72b",
+        "nomic-embed-text",
+        "mxbai-embed-large",
+        "all-minilm",
+        "snowflake-arctic-embed",
     ]
     model_id_key = "model"
 

packages/jupyter-ai-magics/jupyter_ai_magics/providers.py

@@ -728,19 +728,12 @@ class OllamaProvider(BaseProvider, Ollama):
     id = "ollama"
     name = "Ollama"
     model_id_key = "model"
-    models = [
-        "gemma",
-        "gemma2",
-        "llama2",
-        "llama3",
-        "llama3:70b",
-        "phi3",
-        "mistral",
-        "tinyllama",
-        "qwen2",
-        "qwen2:7b",
-        "qwen2:72b",
-    ]
+    help = (
+        "See [https://www.ollama.com/library](https://www.ollama.com/library) for a list of models. "
+        "Pass a model's name; for example, `deepseek-coder-v2`."
+    )
+    models = ["*"]
+    registry = True
 
 
 class JsonContentHandler(LLMContentHandler):